If a call receives an event (such as incoming data), the call gets placed on the socket's queue and a thread in recvmsg can be awakened to go and process it. Once the thread has picked up the call off of the queue, further events will cause it to be requeued, and once the socket lock is dropped (recvmsg uses call->user_mutex to allow the socket to be used in parallel), a second thread can come in and its recvmsg can pop the call off the socket queue again.
In such a case, the first thread will be receiving stuff from the call and the second thread will be blocked on call->user_mutex. The first thread can, at this point, process both the event that it picked call for and the event that the second thread picked the call for and may see the call terminate - in which case the call will be "released", decoupling the call from the user call ID assigned to it (RXRPC_USER_CALL_ID in the control message).
The first thread will return okay, but then the second thread will wake up holding the user_mutex and, if it sees that the call has been released by the first thread, it will BUG thusly:
kernel BUG at net/rxrpc/recvmsg.c:474!
Fix this by just dequeuing the call and ignoring it if it is seen to be already released. We can't tell userspace about it anyway as the user call ID has become stale.
Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code") Reported-by: Junvyyang, Tencent Zhuque Lab zhuque@tencent.com Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Jeffrey Altman jaltman@auristor.com cc: LePremierHomme kwqcheii@proton.me cc: Marc Dionne marc.dionne@auristor.com cc: Jakub Kicinski kuba@kernel.org cc: Paolo Abeni pabeni@redhat.com cc: "David S. Miller" davem@davemloft.net cc: Eric Dumazet edumazet@google.com cc: Simon Horman horms@kernel.org cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org cc: stable@vger.kernel.org --- include/trace/events/rxrpc.h | 3 +++ net/rxrpc/call_accept.c | 1 + net/rxrpc/recvmsg.c | 19 +++++++++++++++++-- 3 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 378d2dfc7392..e7dcfb1369b6 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -330,12 +330,15 @@ EM(rxrpc_call_put_userid, "PUT user-id ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ + EM(rxrpc_call_see_already_released, "SEE alrdy-rl") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ EM(rxrpc_call_see_connected, "SEE connect ") \ EM(rxrpc_call_see_conn_abort, "SEE conn-abt") \ + EM(rxrpc_call_see_discard, "SEE discard ") \ EM(rxrpc_call_see_disconnected, "SEE disconn ") \ EM(rxrpc_call_see_distribute_error, "SEE dist-err") \ EM(rxrpc_call_see_input, "SEE input ") \ + EM(rxrpc_call_see_recvmsg, "SEE recvmsg ") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 226b4bf82747..a4d76f2da684 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -219,6 +219,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->call_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_call *call = b->call_backlog[tail]; + rxrpc_see_call(call, rxrpc_call_see_discard); rcu_assign_pointer(call->socket, rx); if (rx->app_ops && rx->app_ops->discard_new_call) { diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 86a27fb55a1c..6990e37697de 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -447,6 +447,16 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto try_again; }
+ rxrpc_see_call(call, rxrpc_call_see_recvmsg); + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { + rxrpc_see_call(call, rxrpc_call_see_already_released); + list_del_init(&call->recvmsg_link); + spin_unlock_irq(&rx->recvmsg_lock); + release_sock(&rx->sk); + trace_rxrpc_recvmsg(call->debug_id, rxrpc_recvmsg_unqueue, 0); + rxrpc_put_call(call, rxrpc_call_put_recvmsg); + goto try_again; + } if (!(flags & MSG_PEEK)) list_del_init(&call->recvmsg_link); else @@ -470,8 +480,13 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
release_sock(&rx->sk);
- if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) - BUG(); + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { + rxrpc_see_call(call, rxrpc_call_see_already_released); + mutex_unlock(&call->user_mutex); + if (!(flags & MSG_PEEK)) + rxrpc_put_call(call, rxrpc_call_put_recvmsg); + goto try_again; + }
ret = rxrpc_recvmsg_user_id(call, msg, flags); if (ret < 0)